Learning hard quantum distributions with variational autoencoders

Abstract

Studying general quantum many-body systems is one of the major challenges in modern physics because it requires an amount of computational resources that scales exponentially with the size of the system.Simulating the evolution of a state, or even storing its description, rapidly becomes intractable for exact classical algorithms. Recently, machine learning techniques, in the form of restricted Boltzmann machines, have been proposed as a way to efficiently represent certain quantum states with applications in state tomography and ground state estimation. Here, we introduce a new representation of states based on variational autoencoders. Variational autoencoders are a type of generative model in the form of a neural network. We probe the power of this representation by encoding probability distributions associated with states from different classes. Our simulations show that deep networks give a better representation for states that are hard to sample from, while providing no benefit for random states. This suggests that the probability distributions associated to hard quantum states might have a compositional structure that can be exploited by layered neural networks. Specifically, we consider the learnability of a class of quantum states introduced by Fefferman and Umans. Such states are provably hard to sample for classical computers, but not for quantum ones, under plausible computational complexity assumptions. The good level of compression achieved for hard states suggests these methods can be suitable for characterising states of the size expected in first generation quantum hardware.

v2: 9 pages, 3 figures, journal version with major edits with respect to v1 (rewriting of section "hard and easy quantum states", extended discussion on comparison with tensor networks)

References in corpus (6)

• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Quantum Computational Supremacy
• Efficient quantum state tomography
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Chiral Topological Phases from Artificial Neural Networks

Cited by in corpus (38)

• Machine learning and the physical sciences
• A high-bias, low-variance introduction to Machine Learning for physicists
• Discovering physical concepts with neural networks
• Reconstructing quantum states with generative models
• Symmetries and many-body excited states with neural-network quantum states
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Experimental neural network enhanced quantum tomography
• Constructing exact representations of quantum many-body systems with deep neural networks
• Machine learning quantum states in the NISQ era
• Quantum Machine Learning: from physics to software engineering
• Machine Learning for Condensed Matter Physics
• Universal discriminative quantum neural networks
• Modelling Non-Markovian Quantum Processes with Recurrent Neural Networks
• Variational Quantum Circuits for Quantum State Tomography
• Neural-network quantum state tomography
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Revealing quantum chaos with machine learning
• Flexible learning of quantum states with generative query neural networks
• Variational autoencoder reconstruction of complex many-body physics
• Scalable Quantum Tomography with Fidelity Estimation
• Adaptive Quantum State Tomography with Active Learning
• Regression of high dimensional angular momentum states of light
• Neural network approach to quasiparticle dispersions in doped antiferromagnets
• Quantum State Tomography with Conditional Generative Adversarial Networks
• Classification and reconstruction of optical quantum states with deep neural networks
• Direct implementation of a perceptron in superconducting circuit quantum hardware
• Explainable Representation Learning of Small Quantum States
• A novel approach for quantum financial simulation and quantum state preparation
• Probing Criticality in Quantum Spin Chains with Neural Networks
• Efficient factored gradient descent algorithm for quantum state tomography
• Variational Optimization for Quantum Problems using Deep Generative Networks
• Hamiltonian Learning using Machine Learning Models Trained with Continuous Measurements
• Bidirectional information flow quantum state tomography
• Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
• Reinforcement learning to learn quantum states for Heisenberg scaling accuracy
• Learning Minimal Representations of Fermionic Ground States
• Noise-Resilient Quantum Reinforcement Learning